PyData Tel Aviv 2022
| title | author | length |
|---|---|---|
| Numerical Marvels Inside Python - Keynote | Raymond Hettinger | 49m |
Concrete wins and how they are achieved appear: math.factorial drops from microseconds to factorial in nanoseconds by pulling out evens and left‑shifting… | ||
| Extreme Value Analysis | Dimitry Venger | 32m |
Explains how extreme value analysis turns limited records (10–15 years) into one-in-50-year or even 500‑year return value (CI 2.50–5.82) estimates, shows the… | ||
| Simple Data Processing Pipeline | Aviv Zaken | 04m |
xfinda uses a small, practical pipeline that puts processing functions in files and configures runs with YAML mappings, letting analysts map old fields to new… | ||
| Causal Machine Learning – What’s in it for Data Scientists? | Adi Watzman | 06m |
Claims a measurable lift over correlation-only ML by using causal methods to estimate treatment effect (example: which customers actually increase engagement… | ||
| DeepCook: Code Your Way Through Everyday Chores | Avishai Barnoy | 05m |
A small system turns a hand-curated CSV of about 40 meals and rich features — prep time, ingredient flags, recipe links — into deterministic suggestion… | ||
| I Hate writing Tests, That's Why I Use Hypothesis | Cheuk Ting Ho | 30m |
Hypothesis is a Python property-based testing library that uses composable strategies for inputs and demonstrates with a round‑trip encode/decode example that… | ||
| My Family and Other Startups | Efrat Garber Aran | 05m |
Lightning Talk
An amusing and thought provoking spoken word about parenting, High Tech, data and profits.
Follow PyData Tel Aviv… | ||
| GANs: The Case of Predictive Business Process | Rachel Shalom | 29m |
Uses a GAN with LSTM generator/discriminator to predict the next user action on dell.com, trained alternately with binary cross-entropy loss; evaluation uses… | ||
| Quibbler: Your Data - Interactive! | Roy Kishony | 36m |
Concrete claim: Quibbler is an open-source pure-python package that makes ordinary Python analysis live and interactive by turning inputs into tracked “quibs”… | ||
| Notebook To Production | Nir Barazida | 27m |
Seven concrete practices shorten research to production: host code in Python modules so functions are testable and reusable; version everything — code… | ||
| Data Sampling Using Data Maps | Racheli Abo | 26m |
When gathering data to train a ML model, the common belief is ‘the more the merrier’. In reality though, individual data samples may have varying effects on… | ||
| Unleash Big Data Clustering | Tal Erez Hauer | 26m |
I was about to give up my DBSCAN clustering solution when I found out how long it takes to train it with 400 million records. The density-based clustering… | ||
| Synthetic Data in Vision AI: Theory and Practice | Tsvi Lev, Or Katz | 29m |
Synthethic Data Generation is now a popular and important addition to standard image augmentation methods and real life data acquisition and labeling. We will… | ||
| Flexibility General Average for ML | Aleksander Molak, Uri Itai | 31m |
Presents a continuous, differentiable operator called Generalized Average (GA) that interpolates min, max, arithmetic, geometric and harmonic means; shows two… | ||
| Breaking the Privacy-Utility Tradeoff with Deming Regression | Yoel Zeldes, Shuki Cohen | 25m |
Yoel Zeldes & Shuki Cohen
Imagine you’re conducting a salary survey with the goal of training a model to predict the salary. Cool, right? Not if you don’t… | ||
| Keeping Sensitive Data Safe Using Recommendation Systems | Liron Faybish | 26m |
Claim: repurposed recommendation models flag unauthorized database access by scoring each user‑table query and alerting low‑score outliers. Implementation uses… | ||
| Over- and Under-Estimation of Vaccine Effectiveness | Hilla Deleon | 25m |
Claim: failing to account for indirect protection skews vaccine effectiveness estimates. Builds a heterogeneous infection model in Python with periodic… | ||
| Life, Death, and Shopping | Dina Bavli | 27m |
When dealing with survival analysis, the model's success is predicting death correctly. But it can also predict an engine failure, abandonment, or even… | ||
| Distant Annotation for Training Data Preparation | Anna Roitberg | 05m |
Claims that distant supervision produces labeled relation-extraction triples by aligning a knowledge base (Freebase/Wikidata/Wikipedia) with raw text, turning… | ||
| nothing matches | ||